podcast discussion · AI Dev Podcast · TechTrain
AI Dev Podcast #7: Security, Agents, and the Future of Development
June 26, 2026 · AI Dev Podcast · TechTrain
An AI Dev Podcast episode with Evgeny Kokuykin and Alexander Polomodov on the risks of agentic development: GenAI application security, agent quality control, token economics, new SDLC threats, and how engineering work is changing.
Participants
- Andrey Dmitriev · TechTrain, host
- Evgeny Kokuykin · HiveTrace
- Alexander Polomodov · T-Bank
Episode focus
- 01Which risks do agentic systems create for development and security?
- 02How should teams evaluate agent quality through evaluation sets and real-process feedback?
- 03What changes in development economics because of compute, teams, and tokens?
- 04Which new attack chains appear around open source, LLMs, and the SDLC?
- 05Why do agents need separate non-human identities, IAM, and trust boundaries?
- 06When will agents remain assistants, and when can they take on more autonomy?